brahmairesearch
/

x1-7B-v0.1

@@ -1,199 +1,89 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+tags:
+- reasoning
+- transformers
+- maths
+- brahmai
+license: apache-2.0
+datasets:
+- brahmairesearch/x1-exp
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-7B
+pipeline_tag: text-generation
 ---
+# x1 | BRAHMAI
+**7 Billion Parameters | v0.1**
+![x1-7B-v0.1](https://i.ibb.co/dJgyV8H/image.png)
+Introducing **x1-7B-v0.1**, the first Large Language Model by [BRAHMAI](https://brahmai.in) with built-in reasoning capabilities. Based on the powerful **Qwen2.5 7B** architecture, this model has been fine-tuned using a synthetic dataset generated from open-source models across multiple datasets and custom agentic pipelines.
+### Note:
+As the first iteration of this model, **x1-7B-v0.1** demonstrates strong performance in answering reasoning-based questions, making it a valuable tool for advancing further development. When reasoning, the model encapsulates its thought process within `<thinking>` and `</thinking>` tags before delivering the final response.
+---
+### Known Limitations
+While promising, this model has its quirks:
+1. **Unexpected Behavior with Simple Inputs:** For instance, it may break when simply greeted with "Hi."
+2. **Excessive Reasoning:** Even for basic queries, the model often engages in elaborate reasoning chains.
+3. **Repetitive Responses:** Occasionally, after providing an answer, the model gets stuck in a loop, repeating patterns.
+---
+### Example Conversations
+**Note:** All examples were tested with `max_new_tokens` set to 512.
+#### Example 1: Comparing 9.24 and 9.8
+```
+USER: What is larger? 9.24 or 9.8?
+ASSISTANT: <thinking>
+To determine which number is larger between 9.24 and 9.8, we can compare the digits in each place value.
+1. Both numbers have the same digit in the ones place (9).
+2. In the tenths place, 9.24 has a 2, while 9.8 has an 8. Since 8 is greater than 2, 9.8 is larger than 9.24.
+Thus, 9.8 is larger than 9.24.
+</thinking>
+9.8 is larger than 9.24.
+```
+#### Example 2: The "Hi" Scenario
+```
+USER: Hi
+ASSISTANT: <thinking>
+The user is asking for a list of 100 words that start with the letter "S" and end with the letter "e". To generate this list, I need to think of words that fit these criteria.
+I will start by brainstorming words that begin with "S" and end with "e". Some examples include "sage", "sneeze", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve", "sieve",
+```
+#### Example 3: Counting "R"s in "STRAWBERRY"
+```
+USER: How many R's are in STRAWBERRY?
+ASSISTANT: <thinking>
+To determine the number of "R"s in "STRAWBERRY," I’ll count the occurrences of "R."
+The word "STRAWBERRY" consists of the following letters: S, T, R, A, W, B, E, R, R, Y.
+Counting the "R"s:
+- The first "R" is in the third position.
+- The second "R" is in the eighth position.
+- The third "R" is in the ninth position.
+Therefore, there are 3 "R"s in "STRAWBERRY."
+</thinking>
+There are 3 "R"s in the word "STRAWBERRY."
+```
+---
+### Moving Forward
+We're committed to refining this model. Stay tuned for improvements as we continue to fine-tune it.
+If you have any questions or feedback, feel free to reach out to us at [[email protected]](mailto:[email protected]).